Announcement

Collapse
No announcement yet.

AMD FidelityFX Super Resolution 2.0 Source Code Published

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • AMD FidelityFX Super Resolution 2.0 Source Code Published

    Phoronix: AMD FidelityFX Super Resolution 2.0 Source Code Published

    After AMD announced FidelityFX Super Resolution 2.0 back in March, as of today they have made good on their word to open-source it...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Interesting. I expected it to be very slow, but at 1080p/1440p it's quite fast, possibly faster than many other TAA implementations even. Not sure if computing motion vectors and the like factors into that, though.

    Also, typo:
    This temporal uoscaling solution

    Comment


    • #3
      Just a little under 2MB of source code vs ~238MB for NVIDIA DLSS 2.2.

      Comment


      • #4
        I wonder if this can be modified to not need a depth buffer, so it might be applicable to video files with automatically generated motion vectors...

        Comment


        • #5
          I am wondering if it could completely replace TAA implementations in games. One implementation instead of 2, when many games have bad implementations of TAA, maybe it could improve the situation across the board? But can it be used with native resolution?

          Comment


          • #6
            Originally posted by birdie View Post
            Just a little under 2MB of source code vs ~238MB for NVIDIA DLSS 2.2.
            The capabilities of both are entirely different things

            Comment


            • #7
              Originally posted by scottishduck View Post

              The capabilities of both are entirely different things
              Indeed, even more impressive. Being better while being so small.

              Comment


              • #8
                Originally posted by nabero View Post

                Indeed, even more impressive. Being better while being so small.
                This is not what professional reviewers have concluded:



                It's decent, but it's definitely not better.
                Last edited by birdie; 22 June 2022, 11:32 AM.

                Comment


                • #9
                  Cool. It has nothing in common with version 1.
                  Code Looks much cleaner.

                  Comment


                  • #10
                    Originally posted by nabero View Post

                    Indeed, even more impressive. Being better while being so small.
                    From experience I don’t think it looks better. It competes with Nvidia’s Image Scaling along with every other traditional upscaler that’s in game engines. For example UE5 which has Temporal Super Resolution. I’m certain Intel’s XeSS, Nvidia’s DLSS will continue to be in leagues of their own. I know Microsoft/Sony are also working on their own AI upscalers. FaceBook already has their own called neural supersampling. AMD has been working on an AI solution since the release of the Radeon VII.

                    Comment

                    Working...
                    X